Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
hey andreas,
On Tue, May 10, 2005 at 10:29:16AM +0200, Andreas Ericsson wrote:
> In some cases they are. Pure multithreading would do well not to meddle=
=20
> with in-house plugins, since that leaves no means of protection for the=
=20
> core in case the plugin misbehaves (which it's bound to do sooner or late=
r).
yeah, i'd be wary of segfaulting plugins in that case too. =20
> Number of CPU's doesn't matter. It's the number of active processes=20
> that's important. Most of nagios' time is lost idling between two chunks=
=20
> of checks because it doesn't parallellize well enough (one chunk needs=20
> to finish completely before the next can begin). A great improvement=20
> would be to add checks to the queue in serial but letting them run as=20
> they become available.
agreed...
> Nopes, it won't. The forked children just hang around and wait for the=20
> popen call to finish (pclose and fgets both block), which means they=20
> don't claim a CPU and thus aren't eligible for activation in the kernel=
=20
> scheduling loop.
it's true that when the process is in a select/poll/wait or other sleeping
state it won't take up time, but there's still the initial startup cost
of fork/exec'ing the process in the first place. =20
> check_icmp doesn't. I wrote it to increase the abysmal performance of=20
yeah, i was referring to check_ping, which does.
> Ah, the lure of intellectual masturbation.
> I'm looking forward to seeing the code and the benchmarks.
you know, i almost used that phrase myself, but then figured
i might offend someone's sensibilities and/or risk having
google forever associate the word to me
anyway, here's the goods:
http://www.seanius.net/tmp/dltest.tgz
given my recent hijinks, a quick sanity check over my code is probably
in order (in fact i think there is some kind of race in there, maybe).
after that, "make test" will get you the numbers. =20
i found that the overall "real" time was not significantly impacted,
but there does seem to be a modest improvement in user/sys time--and
even more so if you run the test on a slower/busier machine.
sean
--zYM0uCDKw75PZbzx
Content-Type: application/pgp-signature; name="signature.asc"
Content-Description: Digital signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)
iD4DBQFCgWNhynjLPm522B0RAhBcAJj56hPvjk4ZLhtPpGtIsiFsnjpXAJsFvyyg
bxKRi0bvRiFDtuF15fzOJw==
=ypPE
-----END PGP SIGNATURE-----
--zYM0uCDKw75PZbzx--
This post was automatically imported from historical nagios-devel mailing list archives
Original poster: [email protected]